© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 237303
    Prev
    Next
    INDEX
    Explanations

    yellow colored

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     స్టార్
    0.44
     steeds
    0.42
     enshrined
    0.42
    Rd
    0.41
     hypot
    0.41
    crafted
    0.40
     tern
    0.39
    ლ
    0.39
     rd
    0.38
    handleChange
    0.38
    POSITIVE LOGITS
    eku
    0.54
     لئے
    0.51
     لیے
    0.50
     हेल्
    0.48
     স্বীক
    0.47
     Recognition
    0.47
     Produktions
    0.46
     झू
    0.45
     पृ
    0.45
    डून
    0.45
    Activations Density 0.000%

    No Known Activations